Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    visual arrangements of elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anum
    0.37
     nicest
    0.34
     اہمیت
    0.32
     connectedness
    0.31
     Wissenschaften
    0.31
     pretence
    0.31
     хороший
    0.30
     mindset
    0.30
     יש
    0.30
     appreciably
    0.30
    POSITIVE LOGITS
     piles
    0.97
     rows
    0.96
     stacks
    0.87
     clusters
    0.87
     clumps
    0.86
     sheets
    0.84
     bundles
    0.83
     bunches
    0.79
     mounds
    0.79
     streams
    0.78
    Act Density 0.205%

    No Known Activations